© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56015
    Prev
    Next
    INDEX
    Explanations

    secession and shutdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _AUX
    -0.10
     kurs
    -0.10
    ç´ł
    -0.09
    ục
    -0.09
    Ïį
    -0.09
    pollo
    -0.09
    çļĦæĥħå½¢
    -0.09
    æĬĬæı¡
    -0.09
    éĵ£
    -0.09
    ãĤ£
    -0.09
    POSITIVE LOGITS
    ively
    0.11
    æİī
    0.10
    ä¸į说
    0.10
    没æĶ¶
    0.09
     Executive
    0.09
     finest
    0.08
    æļ´åĬĽ
    0.08
    ooled
    0.08
    ä¿Ń
    0.08
    retval
    0.08
    Activations Density 0.002%

    No Known Activations